A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 23:30 UTC
[Bugfix] Only print out chat template when supplied (#13444)
Yuan Tang committed
Feb 18, 2025 at 00:43 UTC
a1074b3efeb908d55468771a348a292850e4d03a
1 file changed
+3
-1
vllm/entrypoints/openai/api_server.py
+3
-1
@@ -797,7 +797,9 @@ async def init_app_state(
797
state.log_stats = not args.disable_log_stats
798
799
resolved_chat_template = load_chat_template(args.chat_template)
800
- logger.info("Using supplied chat template:\n%s", resolved_chat_template)
800
+ if resolved_chat_template is not None:
801
+ logger.info("Using supplied chat template:\n%s",
802
+ resolved_chat_template)
803
804
state.openai_serving_models = OpenAIServingModels(
805
engine_client=engine_client,